Abdullah-Abuolaim/recurrent-defocus-deblurring-synth-dual-pixel
Reference github repository for the paper "Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data". We propose a procedure to generate realistic DP data synthetically. Our synthesis approach mimics the optical image formation found on DP sensors and can be applied to virtual scenes rendered with standard computer software. Leveraging these realistic synthetic DP images, we introduce a new recurrent convolutional network (RCN) architecture that can improve defocus deblurring results and is suitable for use with single-frame and multi-frame data captured by DP sensors.
PythonApache-2.0
Issues
- 0
Code for blur kernel similarity
#7 opened by hjynwa - 0
Depth map
#6 opened by hailanlanlan - 0
Data about camera blur kernel parameters
#5 opened by qylen - 1
the test phase,there are a file lost,"vid_test_samples_list.npy",can you release it?
#4 opened by qylen - 1
Code release?
#2 opened by sieme97 - 1
cut off factor parameter(alpha in paper)
#3 opened by wcy199705 - 1
Synthetic blurring
#1 opened by sieme97